Paper #282

Títol:

A simple randomized algorithm for consistent sequential prediction of ergodic time series

Autors:

László Györfi, Gábor Lugosi i Gusztáv Morvai

Data:

Abril 1998

Resum:

We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.

Paraules clau:

Prediction, ergodic processes, pattern classification

Codis JEL:

C13

Àrea de Recerca:

Estadística, Econometria i Mètodes Quantitatius

Publicat a:

IEEE Transactions on Information Theory, 45, (1999), pp. 2642-2650

Descarregar el paper en format PDF